paper-with-me

Papers

Differentiable Programming à la Moreau

2020-12-31 · Vincent Roulet, Zaid Harchaoui

The notion of a Moreau envelope is central to the analysis of first-order optimization algorithms for machine learning. Yet, it has not been developed and extended to be applied to a deep network and, more broadly, to a machine learning system with a differentiable programming implementation. We define a compositional calculus adapted to Moreau envelopes and show how to integrate it within differentiable programming. The proposed framework casts in a mathematical optimization framework several variants of gradient back-propagation related to the idea of the propagation of virtual targets.

📄 PDF Abstract BibTeX arXiv:2012.15458

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine Learning

Similar Papers 제목 키워드 기반

Bregman Proximal Langevin Monte Carlo via Bregman--Moreau Envelopes

2022-07-10 · Tim Tsz-Kit Lau, Han Liu

We propose efficient Langevin Monte Carlo algorithms for sampling distributions with nonsmooth convex composite potentials, which is the sum of a continuously differentiable function and a possibly nonsmooth function. We…

MoreauGrad: Sparse and Robust Interpretation of Neural Networks via Moreau Envelope

2023-01-08 · ICCV 2023 1 · Jingwei Zhang, Farzan Farnia

Explaining the predictions of deep neural nets has been a topic of great interest in the computer vision literature. While several gradient-based interpretation schemes have been proposed to reveal the influential variab…

MoreauPruner: Robust Pruning of Large Language Models against Weight Perturbations

2024-06-11 · Zixiao Wang, Jingwei Zhang, Wenqian Zhao, Farzan Farnia 외

Few-shot gradient methods have been extensively utilized in existing model pruning methods, where the model weights are regarded as static values and the effects of potential weight perturbations are not considered. Howe…

Moreau Envelope Based Difference-of-weakly-Convex Reformulation and Algorithm for Bilevel Programs

2023-06-29 · Lucy L. Gao, Jane J. Ye, Haian Yin, Shangzhi Zeng 외

Bilevel programming has emerged as a valuable tool for hyperparameter selection, a central concern in machine learning. In a recent study by Ye et al. (2023), a value function-based difference of convex algorithm was int…

Escaping strict saddle points of the Moreau envelope in nonsmooth optimization

2021-06-17 · Damek Davis, Mateo Díaz, Dmitriy Drusvyatskiy

Recent work has shown that stochastically perturbed gradient methods can efficiently escape strict saddle points of smooth functions. We extend this body of work to nonsmooth optimization, by analyzing an inexact analogu…